Review economics
ruvnet/ruflo
Read from the 100 most recently merged pull requests · · read 4 times
Pull requests with attributed agent authorship took 5.8× the time to merge of the rest.
≥4%
Attributed
a floor
5
Attributed PRs
95
Other PRs
100
Read
Attributed — the latest 5
#2863 [Dream Cycle 2026-07-30] performance: Two Calls Beat Five Agents 7.4× token gap + pre-hoc failure inference (ADR-333)
0 reviews · 11h to merge
#2662 fix(daemon): opt-in AI workers, global launch budget, cross-worktree dedup, stop --all (#2661)
0 reviews · 6h to merge
#2589 [Dream Cycle 2026-07-06] security: VMG + RepE IPI detection gaps identified (ADR-178)
0 reviews · 45h to merge
#2538 docs(claude): metallm ask-vs-delegate rule + delegate cost-floor warning
0 reviews · 0h to merge
#2535 docs(claude): enforce gateway-delegated development (meta-llm dev-bridge)
0 reviews · 10h to merge
The rest — the latest 5
#2888 fix(agntcy): pin @agntcy/slim-bindings to the confirmed-working alpha
0 reviews · 0h to merge
#2880 ADR-380 correction: real @agntcy/slim-bindings package + 2 upstream bugs filed
0 reviews · 0h to merge
#2879 ADR-378/379/380: npm Trusted Publishing, statusline segments, AGNTCY/Outshift runtime integration
0 reviews · 0h to merge
#2871 docs(adr): consolidate 49 stale dream-cycle proposals, renumber ADR-334..376
0 reviews · 0h to merge
#2876 chore(release): 3.33.0 — ADR-377 AgentDB Retrieval Security Layer
0 reviews · 0h to merge
How this was measured
4% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work; 2 PRs came off an agent branch with no commit attribution, so the real share runs higher; reads 100 of 526 merged PRs — the rest have not been analyzed yet.
Detected: Claude Code.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read ruvnet/ruflo weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on ruvnet/ruflo — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository